
import pandas as pd 
import pandas_profiling as pp #%pip3 install pandas-profiling 
import matplotlib
import numpy as np
from sklearn.linear_model import LogisticRegression #To be used when you are building predictions on a categorical class. In our case we have two classes. For example if you should have predicted 
                                                    # something against a range, like how warm it is going to be on a given day, that can be any number of values e.g (1-100) then you should use 
                                                    # LinearRegression. 
from sklearn.model_selection import cross_val_score # Used for cross validation, gives us a basic score on how well the model ended up being trained.
from sklearn.model_selection import KFold #Since its default to 5 in the cross validation we import this package for tuning the model.


columns = ["sample", "thickness", "size_unif", "shape_unif", "marginal_adhesion", "epithelial_cell_size", "bare_nuclei", "bland_chromatin","normal_nucleoli","mitoses","class" ] #list of names representing the dataset including in subfile "Names" since the dataset does not have column rows label names in the data file
bc_raw = pd.read_csv("Data/breast-cancer-wisconsin.data", names=columns, na_values=["?"]) # Added na_values=["?"]


bc_raw.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 699 entries, 0 to 698
Data columns (total 11 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   sample                699 non-null    int64  
 1   thickness             699 non-null    int64  
 2   size_unif             699 non-null    int64  
 3   shape_unif            699 non-null    int64  
 4   marginal_adhesion     699 non-null    int64  
 5   epithelial_cell_size  699 non-null    int64  
 6   bare_nuclei           683 non-null    float64
 7   bland_chromatin       699 non-null    int64  
 8   normal_nucleoli       699 non-null    int64  
 9   mitoses               699 non-null    int64  
 10  class                 699 non-null    int64  
dtypes: float64(1), int64(10)
memory usage: 60.1 KB


bc_raw.bare_nuclei.unique()

array([ 1., 10.,  2.,  4.,  3.,  9.,  7., nan,  5.,  8.,  6.])


pp.ProfileReport(bc_raw, progress_bar=False) #This will be embedded in the jupyter notebook, however it is many ways to save is seperatly in either eg html or json.


bc_clean = bc_raw.copy() #copying the raw file


bc_clean.dropna(inplace=True) #This will save memory as it performing the operation on the current dataframe (bc_clean) and give the result without making a copy of it
print(bc_clean.shape)

(683, 11)


bc_clean.drop_duplicates(subset=columns[1:], inplace=True) #drop the 8 duplicates, but not the sample column (0) 
print(bc_clean.shape)

(449, 11)


# Train 90% Test 10% Fold#1-5 <-- Cross validation for each repeat
# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
# learn from the past, to predict the future = predictive skill --> is the ability to accuratly outcome of the data which is never seen before.
# We will use the data (measurements of a breast cancer tumor) from all the columns (features) to train a model, and use this model to later
# predict the Class, meaning it will become either 2 for benign or 4 for malignant on new measurements for other tumors.
# We havent realy pretuned our model. We will try to change the algorithm (solver) By the default it is set to lbfgs.


bc_clean = bc_clean.reset_index(drop=True) #Since we dropped some rows earlier, there exists gap in the index.  We therefore need to re-index starting with 0.


X = bc_clean.loc[:, "thickness":"mitoses"]      #Exluding the sample and class column
y = bc_clean.loc[:, "class"]                   #The answers to all of these predictions in X. Its going to build the model based on the X data values, and compare the performance on the model to the actual answers.
model = LogisticRegression(solver="sag", max_iter=2000)                  #Declare the model. Create an empty logistic Regression variable. 
kfold = KFold(n_splits=3, shuffle=True, random_state=100) #Crossfold #Number of splits (default #5), shuffle is for shuffeling (instead of getting it from top to bottom), and then you also need random state (for seeding correct seq when sharing the ML model). 
results = cross_val_score(model, X, y, cv=kfold) #Returns the accuracy of the folds
print("Accuracy: %.1f%% (%.1f%%)" % (results.mean()*100, results.std()*100))

Accuracy: 95.3% (1.6%)


#We see that this accuracy is very high, and the std is 1,6% (same units) away from each others. 
print(results)

[0.94444444 0.94444444 0.93333333 0.97777778 0.96629213]


pm_model = LogisticRegression() # the default is good enough here
pm_model.fit(X, y)

LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
                   intercept_scaling=1, l1_ratio=None, max_iter=100,
                   multi_class='auto', n_jobs=None, penalty='l2',
                   random_state=None, solver='lbfgs', tol=0.0001, verbose=0,
                   warm_start=False)


import pickle # save the model to a file (see documentation: https://docs.python.org/3/library/pickle.html)


pickle.dump(pm_model, open("pm_model.pkl", "wb")) #saving the file #Write in a binary format


#Load the model as a an object
pm_deploy = pickle.load(open("pm_model.pkl", "rb")) #now we have our model loaded in a object #read binary 

#Our model will now provide a result with given input.
# labs = pd.read_csv(inputdata.csv) # Assume this as a csv file stored as a dataframe without the result (class) which will be used for input

# result = pm_deploy.predict(labs) # Voila. This can also be stored as a web.applicaton or exported to CSV.

Machine Learning introduction and how to create a basic production file¶

Data Import / Setup¶

Update, added "?" as a missing value in the import¶

Data cleansing¶

Model prep¶

Production Model¶

Simulate the use of the model in production¶